Federated Learning for Hybrid Beamforming in mm-Wave Massive MIMO
This work addresses communication efficiency and privacy issues in wireless networks for researchers and engineers, but it is incremental as it applies an existing federated learning approach to a specific domain.
The paper tackles the problem of high communication overhead and privacy concerns in centralized machine learning for hybrid beamforming in mm-Wave massive MIMO by introducing a federated learning framework, demonstrating through simulations that it reduces transmission overhead and is more tolerant to data imperfections compared to centralized methods.
Machine learning for hybrid beamforming has been extensively studied by using centralized machine learning (CML) techniques, which require the training of a global model with a large dataset collected from the users. However, the transmission of the whole dataset between the users and the base station (BS) is computationally prohibitive due to limited communication bandwidth and privacy concerns. In this work, we introduce a federated learning (FL) based framework for hybrid beamforming, where the model training is performed at the BS by collecting only the gradients from the users. We design a convolutional neural network, in which the input is the channel data, yielding the analog beamformers at the output. Via numerical simulations, FL is demonstrated to be more tolerant to the imperfections and corruptions in the channel data as well as having less transmission overhead than CML.